|
{ |
|
"name_or_path": "tclf90/GLM-4.5-Air-AWQ-FP16Mix", |
|
"architectures": [ |
|
"Glm4MoeForCausalLM" |
|
], |
|
"attention_bias": true, |
|
"attention_dropout": 0.0, |
|
"pad_token_id": 151329, |
|
"eos_token_id": [ |
|
151329, |
|
151336, |
|
151338 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"partial_rotary_factor": 0.5, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11264, |
|
"max_position_embeddings": 131072, |
|
"model_type": "glm4_moe", |
|
"moe_intermediate_size": 1408, |
|
"norm_topk_prob": true, |
|
"num_attention_heads": 96, |
|
"n_group": 1, |
|
"topk_group": 1, |
|
"n_routed_experts": 128, |
|
"n_shared_experts": 1, |
|
"routed_scaling_factor": 1.0, |
|
"num_experts_per_tok": 8, |
|
"first_k_dense_replace": 1, |
|
"num_hidden_layers": 46, |
|
"num_key_value_heads": 8, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000, |
|
"num_nextn_predict_layers": 1, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.54.0", |
|
"use_cache": true, |
|
"use_qk_norm": false, |
|
"vocab_size": 151552, |
|
"quantization_config": { |
|
"quant_method": "awq_marlin", |
|
"bits": 4, |
|
"group_size": 128, |
|
"version": "gemm", |
|
"zero_point": true, |
|
"modules_to_not_convert": ["model.embed_tokens", "model.layers.0.", "model.layers.1.", "model.layers.45.", "model.layers.46.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "model.layers.46.mlp.shared_experts.", "model.layers.46.shared_head.", "lm_head"] |
|
} |
|
} |